extract_content_for_rag
Extracts and summarizes web page content for RAG applications, focusing on key details and metadata. Input a URL and optional question to retrieve title, summary, and main content.
Instructions
Extract and summarize web page content optimized for RAG applications.
Args: url: The URL of the page to analyze question: Optional question to focus the extraction on
Returns: Dictionary containing title, summary, main_content, and metadata
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| question | No | ||
| url | Yes |